Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Adventure game graphics with DALL-E 2

hpjansson.org

Post reply on HN
Print view View original

121–130 of 162 posts

Re: Adventure game graphics with DALL-E 2

#121

Post by dfxm12 »

skytrue wrote: post #26

I started off feeling hopeful/excited by OpenAI, GPT-3, DALL-E, etc, as a creator/writer. As time has progressed and I've used these tools and other machine learning tools to create media, I've become disillusioned. It feels as if this is about to explode an existing problem, namely, there's too much content in the world already. Lowering the effort bar for content creation and generation is, in some ways, going to c…

It feels as if this is about to explode an existing problem, namely, there's too much content in the world already. Lowering the effort bar for content creation and generation is, in some ways, going to cause a deluge of low-quality/mid-quality content to be generated.

Like you say, this is an existing situation (I hesitate to call anything that lowers the barrier to entry a "problem"). The printing press opened up printing for more people. As did desktop publishing. Similarly, garage band and bandcamp make it so much easier to produce and publish music. Yeah, there's a ton of books and music out there, including a bunch of junk, but the cream still tends to rise to the top. I'd rather take my chances on having to find a masterpiece in a haystack than have it never get published at all, either because of lack of funding/lack of some specific skill that AI can handle/no willing publisher, etc.

Re: Adventure game graphics with DALL-E 2

#122

Post by CyanBird »

gwd wrote: post #92
CamperBob2 wrote: post #84

Earlier quoted context omitted.

So frustrating that there's no way to access this tech without putting your name on a list and waiting an unspecified amount of time (months?). It's the sort of thing many people would pay well for, even at its current stage of development.

My wait was only 2-3 weeks FWIW.

I am still waiting since they opened the registration

Re: Adventure game graphics with DALL-E 2

#123

Post by usrusr »

usrusr wrote: post #60
ido wrote: post #44

Earlier quoted context omitted.

But the people at OpenAI aren’t doing it as a hobby, they’ve got a lot of money to conduct this research (from Wikipedia: “The organization was founded in San Francisco in late 2015 by Elon Musk, Sam Altman, and others, who collectively pledged US$1 billion.” [1]) This is the misallocation of resources I’m referring to. [1] https://en.wikipedia.org/wiki/OpenAI

And that's all highly speculative, betting on money to somehow show up, for reasons impossible to predict, if only enough games are changed sufficiently hard. If it can be done it will be done, unless we fundamentally change the way we run the economy. Conclusions: (1) Perhaps we should, winning at net zero games is very much a thing in the current way (2) Didn't know it when I started writing this reply (not at all!…

(I meant negative sum games of course, net zero is certainly fine)

Re: Adventure game graphics with DALL-E 2

#126

Post by TuringTest »

bsenftner wrote: post #118
TuringTest wrote: post #110

Earlier quoted context omitted.

My opinion on the problem of "too much content to watch in several lifetimes" will not be solved on the supply side, but the demand side. All content is not created equal: we are social animals and what people around us do interests us much more, even if it is of lower quality. So, if anyone can generate professional-looking creative projects with relative little effort, we'll gravitate towards people creating conten…

Consider the extreme low quality visuals of SouthPark. They used their low quality imagery as joke enhancement for their presenting ideas far more sophisticated than the majority of animated media.

Exactly. And it only took a tool (Flash) that allowed a small team to do what used to require a whole company of trained experts (animated cartoons).

Re: Adventure game graphics with DALL-E 2

#127

Post by GaggiX »

notart666 wrote: post #106
jillesvangurp wrote: post #38

Earlier quoted context omitted.

We're at the beginning of a rapidly evolving situation where out of the blue it is now possible to direct an AI to produce imagery that is interesting using just language. From there to moving animations is a relatively small step and already being worked on. From there to photo realistic scenes directed by just words not that big of a leap either and also something that is being worked on. Are there constraints, gli…

It's not a small step to move from image generation to animation. In fact, it's quite contrare the complexity grows with length, even creating a short would be exponential in cost. GAN Networks cannot and will never be able to do this.

GAN architecture are no longer used expect for small project, they are unstable to train, they usually not cover the whole distribution and they are hard to condition. Nowadays people use diffusion or transformer models.

Re: Adventure game graphics with DALL-E 2

#128

Post by GaggiX »

Sembiance wrote: post #116
CamperBob2 wrote: post #84

Earlier quoted context omitted.

So frustrating that there's no way to access this tech without putting your name on a list and waiting an unspecified amount of time (months?). It's the sort of thing many people would pay well for, even at its current stage of development.

Midjourney is open to everyone now, no waiting, and is easily the 2nd best tool for this stuff

Better than Stable Diffusion? I don't think so, especially in coherence.

Re: Adventure game graphics with DALL-E 2

#129

Post by ZeroGravitas »

hackernewds wrote: post #16
DethNinja wrote: post #13

It looks like AI generated art will be a huge boon for the indie games. Midjourney can definitely lower concept art costs by 5% to 20% as it stands. Nevertheless, AI generated art currently can’t fully eliminate real concept artists.

the obvious disconnect to me has been that we compare DALLE and midjourney results to what we human-generated art used to look like on earlier Unreal Engine. This is what human generated art looks like now: https://youtu.be/JXrWPLNp9tw

Ed Catmull made this animated hand in 1972:

https://www.youtube.com/watch?v=fAhyBfLFyNA

Would anyone in 1972, even Ed Catmull himself, be able to imagine the Youtube video you linked, broadcast globally, for free.

I think these tools are going to be big, but I feel the whole AI thing actually detracts from it. I'd rather think of it like tracing paper or photography than as a replacement for artists.

Re: Adventure game graphics with DALL-E 2

#130

Post by april_22 »

TuringTest wrote: post #110
NegatioN wrote: post #56

Earlier quoted context omitted.

The quality of the upper echelon of art may be raised, but there's still a discovery problem there. Having to sift through stuff to find the gems is already an issue imo. The OP makes a decent (pessimistic) point

My opinion on the problem of "too much content to watch in several lifetimes" will not be solved on the supply side, but the demand side. All content is not created equal: we are social animals and what people around us do interests us much more, even if it is of lower quality. So, if anyone can generate professional-looking creative projects with relative little effort, we'll gravitate towards people creating conten…

I might be wrong, but I could imagine that AI will push the absoulute maximum out of human creativity. To beat AI, you'll truly need to make something outstanding and I think there will be people achieving that and truly pushing the boundaries of creativity and art forward, in ways we haven't seen before. And those people will be rewarded. Everyone will have to step up their game.
Post reply on HN